# Self-Supervised Surgical Tool Segmentation using Kinematic Information

## TL;DR

This paper introduces a self-supervised method for surgical tool segmentation that leverages robot kinematic data to generate training labels, eliminating the need for manual annotations and improving generalization in endoscopic images.

## Contribution

It is the first to utilize robot kinematic models for self-supervised training label generation in surgical tool segmentation.

## Key findings

- Effective segmentation without manual annotations
- Robustness to unknown hand-eye calibration
- Promising results on phantom and in vivo datasets

## Abstract

Surgical tool segmentation in endoscopic images is the first step towards pose estimation and (sub-)task automation in challenging minimally invasive surgical operations. While many approaches in the literature have shown great results using modern machine learning methods such as convolutional neural networks, the main bottleneck lies in the acquisition of a large number of manually-annotated images for efficient learning. This is especially true in surgical context, where patient-to-patient differences impede the overall generalizability. In order to cope with this lack of annotated data, we propose a self-supervised approach in a robot-assisted context. To our knowledge, the proposed approach is the first to make use of the kinematic model of the robot in order to generate training labels. The core contribution of the paper is to propose an optimization method to obtain good labels for training despite an unknown hand-eye calibration and an imprecise kinematic model. The labels can subsequently be used for fine-tuning a fully-convolutional neural network for pixel-wise classification. As a result, the tool can be segmented in the endoscopic images without needing a single manually-annotated image. Experimental results on phantom and in vivo datasets obtained using a flexible robotized endoscopy system are very promising.